Understanding and reproducing DEITA with MantisNLP using distilabel=1.0.0

Argilla
Argilla
166 بار بازدید - 6 ماه پیش - We are very eager to
We are very eager to announce our collaborative community meetup with MantisNLP. We've been working on this wonderful blog series on RLHF and alternatives but in this community edition we will discuss the following: ​- Dissecting the Deita paper is fundamental to getting high-quality data through AI feedback. - ​Using distilabel==1.0.0 for a faithful reproduction of the Deita paper. ​MantisNLP has been a close friend of Argilla so we are really looking forward to this great event. Don't worry, we are also working on an awesome blog about the ORPO paper for our blog series. You can find an overview of the shared documents, chat and QnA here: drive.google.com/drive/folders/1FqEXOTQnz3bvr8Lz7M… Signup for coming meetups here: lu.ma/d720wy9f
6 ماه پیش در تاریخ 1403/01/14 منتشر شده است.
166 بـار بازدید شده
... بیشتر